© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11749
    Prev
    Next
    INDEX
    Explanations

    instances where something is open to or welcoming of various possibilities or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating openness or accessibility to various groups or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bowl
    -0.77
    DK
    -0.72
    irtual
    -0.71
    chem
    -0.68
    yan
    -0.67
    need
    -0.62
     Slug
    -0.62
    ous
    -0.62
    FactoryReloaded
    -0.61
    å¦
    -0.61
    POSITIVE LOGITS
    riott
    0.77
     pasture
    0.75
     conjecture
    0.72
     Pandora
    0.72
     accommodate
    0.71
     interpretation
    0.71
     Doors
    0.68
    pload
    0.68
     breeze
    0.68
    mission
    0.67
    Activations Density 0.080%

    No Known Activations